---
base_model:
- v000000/L3.1-8B-RP-Test-003-Task_Arithmetic
- v000000/L3.1-Niitorm-8B-t0.0001
- Sao10K/L3.1-8B-Niitama-v1.1
- arcee-ai/Llama-3.1-SuperNova-Lite
- akjindal53244/Llama-3.1-Storm-8B
- v000000/L3.1-8B-RP-Test-002-Task_Arithmetic
- grimjim/Llama-3-Instruct-abliteration-LoRA-8B
library_name: transformers
tags:
- mergekit
- merge
- llama
---

*Niitorm's task vectors on Supernova's 405B distilled base. By only changing the vector direction I won't override the distilled 405B logits... I think.*

# merge

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit) and other proprietary tools.

## Merge Details
### Merge Method

This model was merged using the <b>SLERP, Task_Arithmetic and NEARSWAP</b> merge method.

### Models Merged

The following models were included in the merge:
* [v000000/L3.1-Niitorm-8B-t0.0001](https://huggingface.co/v000000/L3.1-Niitorm-8B-t0.0001)
* [Sao10K/L3.1-8B-Niitama-v1.1](https://huggingface.co/Sao10K/L3.1-8B-Niitama-v1.1) + [grimjim/Llama-3-Instruct-abliteration-LoRA-8B](https://huggingface.co/grimjim/Llama-3-Instruct-abliteration-LoRA-8B)
* [akjindal53244/Llama-3.1-Storm-8B](https://huggingface.co/akjindal53244/Llama-3.1-Storm-8B)
* [arcee-ai/Llama-3.1-SuperNova-Lite](https://huggingface.co/arcee-ai/Llama-3.1-SuperNova-Lite)
* [v000000/L3.1-8B-RP-Test-003-Task_Arithmetic](https://huggingface.co/v000000/L3.1-8B-RP-Test-003-Task_Arithmetic)
* [v000000/L3.1-8B-RP-Test-002-Task_Arithmetic](https://huggingface.co/v000000/L3.1-8B-RP-Test-002-Task_Arithmetic) + [grimjim/Llama-3-Instruct-abliteration-LoRA-8B](https://huggingface.co/grimjim/Llama-3-Instruct-abliteration-LoRA-8B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
#Step1 - Add smarts to Niitama with alchemonaut's algorithm.

slices:
  - sources:
      - model: Sao10K/L3.1-8B-Niitama-v1.1+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
        layer_range: [0, 32]
      - model: akjindal53244/Llama-3.1-Storm-8B
        layer_range: [0, 32]
merge_method: nearswap
base_model: Sao10K/L3.1-8B-Niitama-v1.1+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
parameters:
  t:
    - value: 0.0001
dtype: bfloat16
out_type: float16

#Step 2 - Learn vectors onto Supernova 0.4(Niitorm)

models:
  - model: arcee-ai/Llama-3.1-SuperNova-Lite
    parameters:
      weight: 1.0
  - model: v000000/L3.1-Niitorm-8B-t0.0001
    parameters:
      weight: 0.4
merge_method: task_arithmetic
base_model: arcee-ai/Llama-3.1-SuperNova-Lite
parameters:
    normalize: false
dtype: float16

#Step 3 - Fully learn vectors onto Supernova 1.25(Niitorm)

models:
  - model: arcee-ai/Llama-3.1-SuperNova-Lite
    parameters:
      weight: 0.0
  - model: v000000/L3.1-Niitorm-8B-t0.0001
    parameters:
      weight: 1.25
merge_method: task_arithmetic
base_model: arcee-ai/Llama-3.1-SuperNova-Lite
parameters:
    normalize: false
dtype: float16

#Step 4 - Merge checkpoints and keep output/input Supernova heavy
#Merge with a triangular slerp from sophosympatheia.

models:
  - model: v000000/L3.1-8B-RP-Test-003-Task_Arithmetic
merge_method: slerp
base_model: v000000/L3.1-8B-RP-Test-002-Task_Arithmetic+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
parameters:
  t:
    - value: [0, 0, 0.3, 0.4, 0.5, 0.6, 0.5, 0.4, 0.3, 0, 0]
dtype: float16

```

SLERP:
![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f74b6e6389380c77562762/GP2LMRvMkhVJwNDSEC4oU.png)